{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XDO4DPDJRPWMSOMRJT34NAL7EQ","short_pith_number":"pith:XDO4DPDJ","schema_version":"1.0","canonical_sha256":"b8ddc1bc698becc939914cf7c6817f2404b80852352254222d28c2ac527ea4d2","source":{"kind":"arxiv","id":"2307.02009","version":1},"attestation_state":"computed","paper":{"title":"Using Data Augmentations and VTLN to Reduce Bias in Dutch End-to-End Speech Recognition Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Odette Scharenborg, Tanvina Patel","submitted_at":"2023-07-05T03:39:40Z","abstract_excerpt":"Speech technology has improved greatly for norm speakers, i.e., adult native speakers of a language without speech impediments or strong accents. However, non-norm or diverse speaker groups show a distinct performance gap with norm speakers, which we refer to as bias. In this work, we aim to reduce bias against different age groups and non-native speakers of Dutch. For an end-to-end (E2E) ASR system, we use state-of-the-art speed perturbation and spectral augmentation as data augmentation techniques and explore Vocal Tract Length Normalization (VTLN) to normalise for spectral differences due t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.02009","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-05T03:39:40Z","cross_cats_sorted":[],"title_canon_sha256":"d5ff75ea8e886aff7a35a52fdcd5f26a773df8f7a6f1705d424e1233ad2c20a5","abstract_canon_sha256":"86b26dbc6795615c2ab601a7179db67538800e8efe5fb46654ccba241dd42f73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:03.932357Z","signature_b64":"rETVZbFGQgGGaQqJZpsWqCdGp1JdH+2SxjrWndAiU/IfSy8dgflCx5EX7miw89iJafxo2KyMsWpj4wA+k2XMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8ddc1bc698becc939914cf7c6817f2404b80852352254222d28c2ac527ea4d2","last_reissued_at":"2026-07-05T06:28:03.931964Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:03.931964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Data Augmentations and VTLN to Reduce Bias in Dutch End-to-End Speech Recognition Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Odette Scharenborg, Tanvina Patel","submitted_at":"2023-07-05T03:39:40Z","abstract_excerpt":"Speech technology has improved greatly for norm speakers, i.e., adult native speakers of a language without speech impediments or strong accents. However, non-norm or diverse speaker groups show a distinct performance gap with norm speakers, which we refer to as bias. In this work, we aim to reduce bias against different age groups and non-native speakers of Dutch. For an end-to-end (E2E) ASR system, we use state-of-the-art speed perturbation and spectral augmentation as data augmentation techniques and explore Vocal Tract Length Normalization (VTLN) to normalise for spectral differences due t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02009","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.02009/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.02009","created_at":"2026-07-05T06:28:03.932018+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.02009v1","created_at":"2026-07-05T06:28:03.932018+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02009","created_at":"2026-07-05T06:28:03.932018+00:00"},{"alias_kind":"pith_short_12","alias_value":"XDO4DPDJRPWM","created_at":"2026-07-05T06:28:03.932018+00:00"},{"alias_kind":"pith_short_16","alias_value":"XDO4DPDJRPWMSOMR","created_at":"2026-07-05T06:28:03.932018+00:00"},{"alias_kind":"pith_short_8","alias_value":"XDO4DPDJ","created_at":"2026-07-05T06:28:03.932018+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.05885","citing_title":"How to Evaluate Automatic Speech Recognition: Comparing Different Performance and Bias Measures","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XDO4DPDJRPWMSOMRJT34NAL7EQ","json":"https://pith.science/pith/XDO4DPDJRPWMSOMRJT34NAL7EQ.json","graph_json":"https://pith.science/api/pith-number/XDO4DPDJRPWMSOMRJT34NAL7EQ/graph.json","events_json":"https://pith.science/api/pith-number/XDO4DPDJRPWMSOMRJT34NAL7EQ/events.json","paper":"https://pith.science/paper/XDO4DPDJ"},"agent_actions":{"view_html":"https://pith.science/pith/XDO4DPDJRPWMSOMRJT34NAL7EQ","download_json":"https://pith.science/pith/XDO4DPDJRPWMSOMRJT34NAL7EQ.json","view_paper":"https://pith.science/paper/XDO4DPDJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.02009&json=true","fetch_graph":"https://pith.science/api/pith-number/XDO4DPDJRPWMSOMRJT34NAL7EQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XDO4DPDJRPWMSOMRJT34NAL7EQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XDO4DPDJRPWMSOMRJT34NAL7EQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XDO4DPDJRPWMSOMRJT34NAL7EQ/action/storage_attestation","attest_author":"https://pith.science/pith/XDO4DPDJRPWMSOMRJT34NAL7EQ/action/author_attestation","sign_citation":"https://pith.science/pith/XDO4DPDJRPWMSOMRJT34NAL7EQ/action/citation_signature","submit_replication":"https://pith.science/pith/XDO4DPDJRPWMSOMRJT34NAL7EQ/action/replication_record"}},"created_at":"2026-07-05T06:28:03.932018+00:00","updated_at":"2026-07-05T06:28:03.932018+00:00"}